Pith. sign in

REVIEW 3 cited by

A Deep Reinforcement Learning Chatbot

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1709.02349 v2 pith:PJBUN2KA submitted 2017-09-07 cs.CL cs.AIcs.LGcs.NEstat.ML

A Deep Reinforcement Learning Chatbot

Iulian V. Serban , Chinnadhurai Sankar , Mathieu Germain , Saizheng Zhang , Zhouhan Lin , Sandeep Subramanian , Taesup Kim , Michael Pieper
show 10 more authors
Sarath Chandar Nan Rosemary Ke Sai Rajeshwar Alexandre de Brebisson Jose M. R. Sotelo Dendi Suhubdy Vincent Michalski Alexandre Nguyen Joelle Pineau Yoshua Bengio
This is my paper
classification cs.CL cs.AIcs.LGcs.NEstat.ML
keywords learningmodelssystemreinforcementbeenchatbotdatadeep
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MiniLLM: On-Policy Distillation of Large Language Models

    cs.CL 2023-06 conditional novelty 6.0

    MiniLLM distills large language models into smaller ones via reverse KL divergence and on-policy optimization, yielding higher-quality responses with lower exposure bias than standard KD baselines.

  2. Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

    cs.LG 2019-06 unverdicted novelty 6.0

    Develops Way Off-Policy batch RL algorithms with pre-trained model priors, KL-control, and dropout uncertainty estimates to learn implicit rewards from offline human dialog data, reporting live deployment gains over p...

  3. Emotionally-Aware Chatbots: A Survey

    cs.CL 2019-06 unverdicted novelty 1.0

    A survey of emotionally-aware chatbots finding evolution from rule-based to neural methods with most systems including emotion classifiers based on affective resources.